About Me

I am an Assistant Professor of Operations Management at the Zicklin School of Business at Baruch College.

I obtained my PhD in Operations Management at the Data Sciences and Operations department at the USC Marshall School of Business. I was advised by Vishal Gupta and Paat Rusmevichientong in the Operations Management group. Previously, I obtained by M.S. and B.S. in Operations Research at Columbia University.

My research is focused on developing data-driven decision-making methods that utilize decision-aware or end-to-end learning. These methods are essential for solving optimization problems in data scarce settings which arise when:

• Data collection is expensive
• Signal-to-noise ratios are low
• Systems are highly time inhomogeneous.

I am interested in applications in healthcare, transportation, matching, and recommender systems.

Interests. Data-Driven Optimization, Machine Learning

Papers

• Decision-Aware Denoising, Major Revision. with Vishal Gupta, Paat Rusmevichientong

• Decision-Focused Learning with Directional Gradients, NeurIPS, 2024. [paper] with Vishal Gupta
• Debiasing In-Sample Policy Performance for Small-Data, Large-Scale Optimization, Operations Research, 2022. [paper] with Vishal Gupta, Paat Rusmevichientong
• Dynamic server assignment in multiclass queues with shifts, with application to nurse staffing in emergency departments, Operations Research, 2021. [paper] with Carri W. Chan, Vahid Sarhangian
• Extending search phases in the Micali-Vazirani algorithm, 16th International Symposium on Experimental Algorithms, 2017. [code] [paper] with Cliff Stein

• Simplifying the Analysis of the Stein Correction in the Small Data-Large Scale Optimization Regime,

  Technical Note. [paper] with Vishal Gupta, Paat Rusmevichientong

Projects

• Nurse Scheduling App [code] I constructed a data-driven webapp for assigning and scheduling nurses in emergency departments for NewYork–Presbyterian based on congestion levels. In our pilot study, we saw our approach was associated with significant improvements to patient flow including a reduction in average total ED length-of-stay (LOS) of 1.7 hours.
• Optimizing Customer Satisfaction for E-Commerce: A Logistics Approach Citadel Correlation One National Championship Datathon submission that studied how improving logistics in for the Brazilian e-commerce company Olist can improve customer satisfaction. We studied how earlier package arrival and reducing the number of shipments improved customer satisfaction. We then used insights to prescribe potential regions in Brazil where Olist should expand their existing supply chain to improve customer satisfaction while optimizing their growth in the Brazilian market